vscode-dev-workbench

Use when the user wants to run the vscode.dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local `microsoft/vscode` sources. Covers starting the dev server, the `vscode-quality=dev` URL, browser-driven interaction patterns, and optionally wiring up a local mock agent host for the Agents window.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill body that assumes Claude's competence and provides copy-paste-ready commands and snippets with real validation checkpoints. The weakest area is conciseness/structure: a few inline blocks are heavy enough that a separate reference file would improve navigation and token efficiency.

Suggestions

Move the CDP mobile-emulation snippet and the mock-agent expected-log listing into a reference file (e.g. references/automation.md) and link to it from SKILL.md to tighten the overview and improve progressive_disclosure.

Trim explanatory asides Claude already knows (e.g. 'The chat input is a Monaco editor') to lift conciseness toward a lean 5.

Add a short numbered quick-start checklist at the top (clone siblings -> npm run dev from vscode-dev -> curl readiness -> open URL) with explicit validate-then-proceed gates to make the primary workflow a tighter sequence.

Dimension	Reasoning	Score
Conciseness	Dense and competence-assuming with no basic-concept padding, but carries a few explanatory asides ('The chat input is a Monaco editor') and a verbose inline mock-agent log listing that could be trimmed.	4 / 5
Actionability	Fully executable throughout: copy-paste commands (npm run dev, pushd && pwd && npm run dev, the agentHostServerMain.js invocation), ready-to-run JS snippets, exact URLs, an exact CSS selector, and concrete env-var examples covering the common cases.	5 / 5
Workflow Clarity	Clear sectioned sequence with explicit checkpoints (readiness curl returning 200, ordered expected mock-agent logs, missing-file prerequisite) and a symptom/cause/fix troubleshooting table, but the primary flow is sectioned rather than a tight numbered validate-then-proceed checklist.	4 / 5
Progressive Disclosure	Single self-contained file with clear section headers and only one-level-deep source-file pointers ('see mockAgent.ts'); well-organized, though some heavier inline material (CDP mobile snippet, mock-agent log list) could live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with an explicit 'Use when' trigger and multiple concrete capabilities. It is strong overall; the main improvement would be making the trigger clause enumerate more concrete user-facing phrases rather than a single general condition.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('starting the dev server', 'the vscode-quality=dev URL', 'browser-driven interaction patterns', 'mock agent host') with named artifacts, with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Covers starting the dev server... mock agent host') and 'when' ('Use when the user wants to run...'), but the trigger is a single general clause rather than concrete enumerated trigger phrases.	4 / 5
Trigger Term Quality	Includes natural phrases a developer would say ('run the vscode.dev server locally', 'exercise the VS Code workbench or Agents window', 'integrated browser', 'local microsoft/vscode sources') with good coverage, though it leans technical and omits some synonym variations.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (running vscode.dev locally against sibling microsoft/vscode sources) with distinct triggers and minimal realistic overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: posit-dev/positron
Path: .github/skills/vscode-dev-workbench/SKILL.md
Commit: 75a1182

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.